Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    verbs related to actions or events

    oai_token-act-pair · gpt-3.5-turbo

    gerunds or present participles that indicate ongoing actions or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    si
    -0.58
    so
    -0.52
    mpeg
    -0.52
    dt
    -0.51
    behind
    -0.50
    ère
    -0.49
    talk
    -0.49
    ombat
    -0.48
    ega
    -0.48
    asia
    -0.47
    POSITIVE LOGITS
    redients
    0.80
    tons
    0.71
     oneself
    0.67
    HAM
    0.64
    BuyableInstoreAndOnline
    0.58
     engagements
    0.57
    GGGGGGGG
    0.57
     Pengu
    0.56
    AME
    0.55
    issance
    0.54
    Act Density 0.693%

    No Known Activations